{"title":"InstanceNorm2d","height":"190","categories":["DL"],"author_name":"HTN20190109","provider_url":"https://hatena.blog","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fhtn20190109.hatenablog.com%2Fentry%2F2025%2F11%2F30%2F162045\" title=\"InstanceNorm2d - HTN20190109\u306e\u65e5\u8a18\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","author_url":"https://blog.hatena.ne.jp/HTN20190109/","version":"1.0","blog_url":"https://htn20190109.hatenablog.com/","url":"https://htn20190109.hatenablog.com/entry/2025/11/30/162045","provider_name":"Hatena Blog","published":"2025-11-30 16:20:45","width":"100%","description":"import torchimport torch.nn as nn # --- \u30e2\u30c7\u30eb\u5b9a\u7fa9 ---class Model(nn.Module): def __init__(self): super().__init__() self.main = nn.Sequential( nn.Conv2d(1024, 1024, kernel_size=7, stride=2, padding=3, bias=False), nn.InstanceNorm2d(1024), nn.LeakyReLU(0.2) ) self.last = nn.Sequential( nn.Conv2d(1024, 1,\u2026","blog_title":"HTN20190109\u306e\u65e5\u8a18","image_url":null,"type":"rich"}